Enter your keyword

2-s2.0-85101581875

[vc_empty_space][vc_empty_space]

Anomaly Behavior Detection of Angkot Based on Transportation Data

Nurmalasari R.R.a, Putri E.P.a, Prihatmanto A.S.a, Yusuf R.a, Wijaya R.b

a Bandung Institute of Technology, School of Electrical Engineering and Informatics, Bandung, Indonesia
b Telkom University, Faculty of Electrical Engineering, Bandung, Indonesia

[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2020 IEEE.Public transportation in Indonesia as a developing country differs from developed country, and there is a certain public transportation called angkot (angkutan kota, or city transport), which became the focus of our research. This paper presents the experiments on data transportation to analyze and detect anomaly behavior of angkot. The focus is on discussing the results of experiments to calculate the length of waiting time for angkot at hotspots, clustering of angkot trips patterns and building a model to detect anomaly behavior of angkot. The results of the review and experiment indicate the length of the time needed for angkot in waiting for the passengers and show which angkot that exceeds the normal time limit set by the government in waiting for the passengers, which suggests a deviant behavior. The results for clustering angkot that have similiar trips patterns using principal component analysis and K-Means give fairly high accuracy. The result for detection of anomaly behavior using autoencoder and Long Short-Term Memory (LSTM) can be used to detect anomaly behavior of angkot when data are collected without labels. The results of the evaluation of model have a loss mean absolute error (MAE) value which is getting smaller. In addition, the output data from the detection of anomaly behavior using autoencoder and LSTM will automatically be labeled true or false, which indicates true if there is an anomalous behavior, while false if there is no anomaly behavior.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Anomalous behavior,Auto encoders,Behavior detection,City transport,Developed countries,High-accuracy,Mean absolute error,Public transportation[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]anomaly behavior,autoencoder,big data analysis,K-Means,LSTM,PCA,trips pattern,waiting time[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICIDM51048.2020.9339658[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]